Whatsapp Bot MCP

🚀 NiagaBot - Smart WhatsApp Business Automation

NiagaBot is a smart WhatsApp bot for business automation that uses AI Qwen3-Omni. This bot helps you automate business communication, broadcasting, message scheduling, auto-replying, and much more!

Your Smart Business Automation Companion powered by Advanced AI

✨ Features

🤖 AI Smart Automation

• Multimodal AI: Process text, images, audio, and video with Qwen3-Omni AI.
• Smart Auto-Response: Automatically reply to customer messages.
• Chat Flow Builder: Build conversation flows for customer service.

📣 Broadcast & Marketing

• Mass Broadcast: Send messages to many customers simultaneously.
• Scheduled Messages: Schedule messages to be sent later.
• Progress Tracking: Monitor real-time sending status.

👥 Group Management

• Welcome/Farewell Messages: Automatically greet new members.
• Anti-Spam Protection: Keep your groups clean and safe.
• Group Synchronization: Easily manage multiple groups.

📊 Analytics & Reporting

• Comprehensive Dashboard: Monitor all your bot activities.
• Statistics & Metrics: Analyze message and broadcast performance.
• Export Data: Export analytics to CSV/JSON.

🔐 Enterprise Features

• Multi-User Support: Team collaboration with role-based access.
• REST API: Integrate with other systems.
• Web Dashboard: A beautiful and easy control panel.
• Secure Authentication: JWT-based security.

Architecture

WhatsApp Web (Browser Automation)
          ↓
   WhatsApp Bot Core
          ↓
  Qwen3-Omni Integration
    ↙              ↘
Local Model    DashScope API

Prerequisites

• Node.js (v16 or higher)
• npm or yarn
• A WhatsApp account for testing
• (Optional) A DashScope API key for cloud-based Qwen3-Omni access

📦 Installation

1. Clone the repository:

git clone <repository-url>
cd whatsapp-bot-mcp

2. Install dependencies:

npm install

Configuration

The bot can be configured in two ways:

Option 1: Local Model (Resource Intensive)

To run Qwen3-Omni locally, you'll need:

• A high-end GPU (32GB+ VRAM recommended)
• A significant amount of RAM (64GB+ recommended)
• A proper Python environment with required dependencies

This option requires installing additional dependencies that are not included in this package due to their size and complexity.

Option 2: Alibaba Cloud/DashScope API (Recommended for Most Users)

This is the easiest way to use Qwen3-Omni without the need for high-end hardware:

Option A: Through DashScope (Easy Version)

1. Sign up for an account at DashScope.
2. Get your API key from the dashboard:
   • Visit the DashScope Console.
   • Navigate to the "API Keys" section.
   • Create a new API key or use an existing one.
3. Update config.json:

{
  "dashscope": {
    "enabled": true,
    "apiKey": "your-api-key-here",
    "model": "qwen3-omni"
  }
}

Option B: Through Alibaba Cloud (For Enterprise Users)

1. Sign up for an account at Alibaba Cloud.
2. Enable the DashScope or ModelStudio service.
3. Get the access key through the Alibaba Cloud console.
4. Use the appropriate API endpoint:

{
  "dashscope": {
    "enabled": true,
    "apiKey": "your-access-key-here",
    "model": "qwen3-omni",
    "apiEndpoint": "https://dashscope.aliyuncs.com/api/v1"
  }
}

How to Get Your API Key:

1. Sign up for an account:

   • For DashScope: dashscope.aliyuncs.com.
   • For Alibaba Cloud (global): Alibaba Cloud.

2. Get your API key:

   • Visit the DashScope Console.
   • Navigate to the "API Keys" section.
   • Create a new API key or use an existing one.
   • Copy the API key for use in your configuration.

3. Secure Storage of API Key (Recommended): Instead of hardcoding your API key in configuration files, use environment variables:

# Set environment variable (Linux/Mac)
export DASHSCOPE_API_KEY="your-api-key-here"

# Set environment variable (Windows)
set DASHSCOPE_API_KEY="your-api-key-here"

# Or create a .env file in your project directory
echo "DASHSCOPE_API_KEY=your-api-key-here" > .env

Then reference it in your config.json:

{
  "dashscope": {
    "enabled": true,
    "apiKey": null,
    "model": "qwen3-omni"
  }
}

Alternatively, you can copy the example configuration file and edit it:

cp config.example.json config.json
# Then edit config.json with your API key

Free Tier & Pricing:

• DashScope offers a free tier with limited usage for getting started.
• Pay-as-you-go pricing for higher usage requirements.
• Check the DashScope pricing page for current rates.

Security Best Practices

When using the DashScope API, follow these security best practices:

1. Never commit API keys to version control

   • Add .env and config.json to your .gitignore file.
   • Use environment variables instead of hardcoded keys.

2. Use environment variables for API keys

# Create .env file
echo "DASHSCOPE_API_KEY=your-api-key-here" > .env

# Add to .gitignore
echo ".env" >> .gitignore

3. Limit API key permissions

   • Create keys with minimal required permissions.
   • Use different keys for different environments (development, staging, production).

4. Monitor API usage

   • Regularly check your usage in the DashScope console.
   • Set up alerts for unusual activity or usage spikes.

5. Rotate keys regularly

   • Change your API keys periodically.
   • Immediately rotate any compromised keys.

💻 Usage Examples

Basic Usage

1. Start the bot:

npm start

2. Scan the QR code with your WhatsApp mobile app to log in.

3. The bot will start monitoring for messages and responding using Qwen3-Omni.

How It Works

1. Message Monitoring: The bot continuously checks for new messages in WhatsApp Web.
2. Message Processing: Incoming messages (text or media) are processed by Qwen3-Omni.
3. Response Generation: Qwen3-Omni generates appropriate responses based on the input.
4. Response Sending: Responses are sent back through WhatsApp Web.

Qwen3-Omni Capabilities

Qwen3-Omni provides advanced multimodal processing including:

• Text Understanding: Process and respond to text messages in multiple languages.
• Image Analysis: Analyze images and respond to visual content.
• Audio Processing: Transcribe and understand audio messages.
• Video Understanding: Process video content with both visual and audio analysis.
• Multimodal Reasoning: Combine information from multiple modalities for comprehensive understanding.
• Real-time Interaction: Stream responses in both text and natural speech.
• Multilingual Support: Supports 119 text languages, 19 speech input languages, and 10 speech output languages.

Supported Modalities

1. Text: Process natural language queries, conversations, and document analysis.
2. Images: Recognize objects, scenes, text (OCR), and visual elements.
3. Audio: Speech recognition, music analysis, sound classification, and audio captioning.
4. Video: Video description, scene analysis, and audio-visual understanding.

Voice Options

When using audio generation capabilities, Qwen3-Omni supports multiple voice options:

• Ethan: A bright, upbeat male voice with infectious energy.
• Chelsie: A honeyed, velvety female voice with gentle warmth.
• Aiden: A warm, laid-back male voice with boyish charm.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

• Qwen3-Omni by Tongyi Lab
• DashScope API for cloud-based AI access
• Playwright/Puppeteer for browser automation
• Model Context Protocol for tool integration

Benefits of Using Alibaba Cloud/DashScope

See the detailed benefits of using Alibaba Cloud or DashScope for Qwen3-Omni access.